Instructions to use SakanaAI/Llama-3-8B-Instruct-Coding-Expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SakanaAI/Llama-3-8B-Instruct-Coding-Expert with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="SakanaAI/Llama-3-8B-Instruct-Coding-Expert")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SakanaAI/Llama-3-8B-Instruct-Coding-Expert")
model = AutoModelForCausalLM.from_pretrained("SakanaAI/Llama-3-8B-Instruct-Coding-Expert")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SakanaAI/Llama-3-8B-Instruct-Coding-Expert with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SakanaAI/Llama-3-8B-Instruct-Coding-Expert"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakanaAI/Llama-3-8B-Instruct-Coding-Expert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SakanaAI/Llama-3-8B-Instruct-Coding-Expert

SGLang

How to use SakanaAI/Llama-3-8B-Instruct-Coding-Expert with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "SakanaAI/Llama-3-8B-Instruct-Coding-Expert" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakanaAI/Llama-3-8B-Instruct-Coding-Expert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "SakanaAI/Llama-3-8B-Instruct-Coding-Expert" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SakanaAI/Llama-3-8B-Instruct-Coding-Expert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SakanaAI/Llama-3-8B-Instruct-Coding-Expert with Docker Model Runner:
```
docker model run hf.co/SakanaAI/Llama-3-8B-Instruct-Coding-Expert
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🐟 Llama-3-CycleQD

🤗 Models | 📚 Paper | 🐦 Twitter

This collection of agentic Language Models (LLMs) is based on Llama-3-8B-Instruct. Llama-3-8B-Instruct-CycleQD-CS is created using the CycleQD method, which leverages:

Please refer to our report for more details. We are grateful to the developers of the following source model and training data:

Model Details

Developed by: Sakana AI
Model type: Autoregressive Language Model
License: META LLAMA 3 COMMUNITY LICENSE
Repository: SakanaAI/CycleQD
Paper: https://arxiv.org/abs/2410.14735

Uses

This model is provided for research and development purposes only and should be considered as an experimental prototype. It is not intended for commercial use or deployment in mission-critical environments. Use of this model is at the user's own risk, and its performance and outcomes are not guaranteed. Sakana AI shall not be liable for any direct, indirect, special, incidental, or consequential damages, or any loss arising from the use of this model, regardless of the results obtained. Users must fully understand the risks associated with the use of this model and use it at their own discretion.

Acknowledgement

We would like to thank the developers of the source models and training datasets for their contributions and for making their work available. These models are based on results obtained from a project, JPNP20017, subsidized by the New Energy and Industrial Technology Development Organization (NEDO), and built with Meta Llama 3.

Citation

@article{sakana2024cycleQD,
  title={Agent Skill Acquisition for Large Language Models via CycleQD},
  author={So Kuroki and Taishi Nakamura and Takuya Akiba and Yujin Tang},
  year={2024},
  eprint={2410.14735},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2410.14735},
}